BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Enhancing Video Generation with Explicit 3D Guidance for Accurate 
 Motion Simulation - fy277@cam.ac.uk
DTSTART:20240229T140000Z
DTEND:20240229T150000Z
UID:TALK212167@talks.cam.ac.uk
CONTACT:Rafal Mantiuk
DESCRIPTION:Video generation is currently a highly popular task. However\,
  common video generation models rely solely on large-scale data training t
 o implicitly simulate motion\, which can sometimes result in inaccuracies.
  To address this problem\, we propose utilizing explicit 3D guidance to gu
 ide the video generation process. Given a single image and the user’s mo
 tion demands\, we model the object and motion in 3D\, allowing for renderi
 ng from various viewpoints. Subsequently\, we inject the motion prior from
  these rendered views into the video generation model in producing high-qu
 ality videos with the desired motion.\n\nZoom link: https://cam-ac-uk.zoom
 .us/j/89792055791?pwd=OTYyQXdnUXZMcnU4VmZWL2p4dUhZdz09
LOCATION:SS03 - William Gates Building
END:VEVENT
END:VCALENDAR